punica-ai/punica

Serving multiple LoRA finetuned LLM as one

41
/ 100
Emerging

This project helps developers serve many specialized Large Language Models (LLMs) from a single system efficiently. It takes in requests for different fine-tuned LLMs and provides their specific responses, enabling developers to offer a wide range of AI services without excessive hardware costs. It's for developers building and managing AI applications that use custom, fine-tuned LLMs for various tasks.

1,145 stars. No commits in the last 6 months.

Use this if you are a developer serving multiple custom, fine-tuned Large Language Models and need to maximize throughput and minimize latency with shared resources.

Not ideal if you are only running a single LLM or don't need to serve custom, fine-tuned models.

AI-service-deployment LLM-fine-tuning AI-infrastructure model-serving GPU-optimization
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

1,145

Forks

61

Language

Python

License

Apache-2.0

Category

llm-fine-tuning

Last pushed

May 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/punica-ai/punica"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.